- Scientists at the University of Southampton have developed an AI platform called CenSegNet to uncover microscopic patterns within breast cancer tumours.
- The tool analysed over 330,000 centrosomes from tissue samples of 127 breast cancer patients treated at University Hospital Southampton.
- The AI identified two distinct centrosome defects that behave independently: an excess count of centrosomes and abnormally enlarged centrosomes.
- Tumours with high levels of enlarged centrosomes were found to be more aggressive, while lower levels correlated with higher patient survival rates.
- Researchers believe the platform could enable better forecasting of disease progression, new biomarkers and more personalised treatment strategies.
IN FULL
